linux_china技术雷达linux_china技术雷达

ChatGPT

ainew
采用

ChatGPT是OpenAI推出AI产品，官方介绍为Get instant answers, find creative inspiration, learn something new， 此处省去5千字介绍。

对于开发人员来说，我们觉得更需要了解以下一些知识：

  • OpenAI API: https://platform.openai.com/docs/api-reference
  • 提示工程(Prompt Engineering): 要学会如何更快更好地问问题，Garbage in, garbage out是AI的哲学。
  • Assistants Tools: 自定义的函数调用，之前名称为functions，现在命名为tools

使用AI时，System Message 扮演着非常重要的角色， 理论上你需要进行相关的设计，如下述就是一个Java项目的system message：

I am linux_china, a senior Java developer. I have strong experience with the following technology stacks:

- Language: Java 17
- Build tool: Apache Maven 3
- Frameworks: Spring Boot 3, Spring Cloud, Spring Data JPA
- Libraries:
  - Apache Commons IO: a library of utilities to assist with developing IO functionality
  - Apache Commons Codec: encoder and decoders for various formats such as Base64, digest and Hexadecimal
  - Apache Commons Lang 3.0: helper utilities for the java.lang API, notably String manipulation methods, basic numerical methods, object reflection, concurrency, creation and serialization and System properties
  - Guava: Google Core Libraries for Java, includes new collection types (such as multimap and multiset), immutable collections, a graph library, and utilities for concurrency, I/O, hashing, primitives, strings, and more!
  - Jackson: Java JSON library with JSON serializer and deserializer by ObjectMapper
  - MyBatis: first class persistence framework with support for custom SQL
- Database: PostgreSQL, Redis
- Messaging: Apache Kafka
- Unit Test: JUnit 5, AssertJ, DbUnit
- Architecture: Domain-Driven Design(DDD)

Now I'm developing a web application focusing on KMS(key management service).

对来项目来说，通常你需要描述好你个人的经验和项目相关的信息，这样AI就可以很好地进行回答。

当你完成system message后，在末尾添加一个新的一行： Could you understand all of these technologies? If you have any questions, please let me know. ，然后发送给AI，如果有一些不明确的地方，可以再进行调整。

OpenAI Code Interpreter

Code Interpreter是OpenAI推出的一个新功能， 可以帮助你生成并执行代码。 OpenAI Code Interpreter沙箱的环境和支持的地方开发包如下：

ChatGPT & Friends

References